© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94793
    Prev
    Next
    INDEX
    Explanations

    odds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pioneer
    -0.09
     Helen
    -0.08
     уз
    -0.08
     пл
    -0.08
    bien
    -0.08
     vê
    -0.08
     Pioneer
    -0.08
     Derby
    -0.08
     lant
    -0.07
    bt
    -0.07
    POSITIVE LOGITS
     odds
    0.08
     favorable
    0.08
     facts
    0.08
     wr
    0.07
     analyt
    0.07
    赔率
    0.07
    flip
    0.07
     favourable
    0.07
    .flip
    0.07
     Cu
    0.07
    Activations Density 0.003%

    No Known Activations